检索结果-内蒙古大学图书馆

Behavioral-based real-time cheating detection in academic exams using deep learning techniques

AIP Conference Proceedings 2023年第1期2909卷

作者： Zouheir Trabelsi Medha Mohan Ambali Parambil Fady Alnajjar Luqman Ali Department of Information Systems and Security College of Information Technology United Arab Emirates University Al Ain United Arab Emirates Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain United Arab Emirates

Recently, with the development of Artificial Intelligence (AI), the use of automated evaluation in education has increased. Maintaining academic integrity is one of the most challenging aspects of higher education. Cheating is rampant in academic examinations and other forms of educational assessment. The vast majority of students believe that it is unethical to tolerate cheating; therefore, it is vital to devote a significant amount of effort to identifying and avoiding instances of cheating. Examining the student’s behavior is one way to determine whether they are engaged in cheating or not. This paper proposes a deep learning-based cheating detection system that can identify instances of students engaging in dishonest behavior. A YOLOv7 model is trained on a custom dataset collected from various resources. The dataset comprises two classes, i.e., cheating and not cheating, and 2565 images. Evaluation criteria like precision, F1 score, recall, and mAP (mean average precision) are used to validate the performance of the proposed model. The proposed model shows promising performance in categorizing the student’s visible actions into cheating or not cheating and achieved an overall mAP@0.5 of 0.719. Overall, the proposed method can be utilized to reduce the error rate associated with human monitoring by alerting the proper authorities whenever unusual behavior is observed during academic tests.

关键词：

来源：评论

学校读者我要写书评

暂无评论

E-learning Model for Students' Satisfaction in Higher Education Universities: Review Paper

E-learning Model for Students' Satisfaction in Higher Educat...

引用

2019 International Conference on Fourth Industrial Revolution, ICFIR 2019

作者： Tawafak, Ragad M Romli, Awanis B.T. Arshah, Ruzaini Bin Abdullah Faculty of Computer Systems and Software Engineering University Malaysia Pahang Kuantan Pahang26300 Malaysia Faculty of Information Technology Department AlBuraimi University College Buraimi Oman

ISBN: (纸本)9781728114781

The number of internet users with E-Learning models offered in high educational institutions has increased rapidly with the beginning of this century. However, with the increment in number of higher education in the universities, the learner needs more flexibility to attend lesions and easy participate in communication. Therefore, E-Learning is one of the ways provide an accessibility and flexibility to more learners to overcome the far distance of locations or different cultures or timing management for achieving student satisfaction. This paper aims to analyze the current studies on benefits of E-Learning of student satisfaction on the technologies applied and type of blended learning used in learning process to get better qualified learners and to improve the student learning outcomes. The method based on showing different types of E-Learning strategies and the way that allowed learners and faculties to communicate using the common communication models. The finding of this paper shows analytical studies results and their positive evidence with student satisfaction on E-Learning models. © 2019 IEEE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Accessing Provenance Records in Semantic Web Services

Accessing Provenance Records in Semantic Web Services

引用

International Conference on Semantic Computing

作者： Omar Ochoa Miralda Rodney Nicholas Del Rio Department of Electrical Computer Software & Systems Engineering Embry-Riddle Aeronautical University Daytona Beach FL USA Air Force Research Laboratory Rome NY USA

ISBN: (数字)9781728163321

ISBN: (纸本)9781728163338

Provenance on the Semantic Web provides information about the creation, publication and access of resources. Provenance and provenance metadata records from a resource are used to determine trust, to integrate diverse information about the resource and to determine how to credit originators when reusing information. Web services make resources available over the internet by using standardized communication services to automatically exchange data between applications and various systems. The World Wide Web consortium (W3C) proposed the Provenance Access and Query (PROV-AQ) that recommends how to represent and exchange provenance information about resources though a standardized communication protocol. Integrating semantics into web-based service descriptions enables agents to more quickly assemble, discover, and reuse arbitrary web services and the information retained within. The addition of provenance information as part of a Semantic Web service would further increase the reuse and discovery of information and trust on the Web when determining which services to employ in each application. In this paper, the provenance of a resource is tracked using a semantic version control tool with a query interface. The underlying data is made available through a web service using provenance access and query to associate the service to its provenance records. Furthermore, the implications of integrating provenance into a Semantic Web service are discussed. Findings from the literature review and developing a Semantic Web service that exposes provenance records, indicate few differences with a Semantic Web service without attaching provenance records.

关键词： Web services Semantic Web Semantics Ontologies Protocols Standards Tools

来源：评论

学校读者我要写书评

暂无评论

Evaluation of deep segmentation models for the extraction of retinal lesions from multi-modal retinal images

arXiv

引用

arXiv 2020年

作者： Hassan, Taimur Akram, Muhammad Usman Werghi, Naoufel Center for Cyber-Physical Systems Khalifa University Abu Dhabi United Arab Emirates Department of Computer and Software Engineering National University of Sciences and Technology Islamabad Pakistan

Identification of lesions plays a vital role in the accurate classification of retinal diseases and in helping clinicians analyzing the disease severity. In this paper, we present a detailed evaluation of RAGNet, PSPNet, SegNet, UNet, FCN-8 and FCN-32 for the extraction of retinal lesions such as intra-retinal fluid, sub-retinal fluid, hard exudates, drusen, and other chorioretinal anomalies from retinal fundus and OCT scans. We also discuss the transferability of these models for extracting retinal lesions by varying training-testing dataset pairs. A total of 363 fundus and 173,915 OCT scans were considered in this evaluation from seven publicly available datasets from which 297 fundus and 59,593 OCT scans were used for testing purposes. Overall, the best performance is achieved by RAGNet with a mean dice coefficient (DC) score of 0.822 for extracting retinal lesions. The second-best performance is achieved by PSPNet (mean DC: 0.785) using ResNet50 as a backbone. Moreover, the best performance for extracting drusen is achieved by UNet (DC: 0.864). The source code is available at: http://***/***/downloads/. Copyright © 2020, The Authors. All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

A self-organizing efficient power generation system in extreme condition for Waggle

A self-organizing efficient power generation system in extre...

引用

IEEE Sensors Applications Symposium, SAS

作者： Surin Jo Jaemin Nam Minju Kang Kar Ee Ho Eric T. Matson Department of Smart Systems Software Soongsil University Seoul Republic of Korea Department of Computer Engineering Yonsei University Wonju Republic of Korea Department of Computer Education Jeju National University Jeju Republic of Korea Department of Computer and Information Technology Purdue University West Lafayette IN USA

ISBN: (数字)9781728148427

ISBN: (纸本)9781728148434

To deploy a novel wireless sensor platform in non-urban area, great consideration must be taken on its powering system. This paper describes an autonomous power generation system in extreme weather such as winter cold, summer heat, and other natural events. The system was designed to apply to the Waggle Stack. The Waggle platform, a research project from Argonne National Laboratory is one of the most practical autonomous nodes allowing for the collection of environmental data in an urban area. Previous work on Waggle's power system stopped at a limitation of 3.17 hours of operation when all modules were on. Our power system lasted for 8 hours which is 2.5 times as long as the previous one. This paper examines the power system to provide continuous power and remain operational 24 × 7 × 365, regardless of the environmental *** measuring the system's performance through state-of-charge checking of the battery in this project, we tested the improved structure of the power system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph-Based File Dispatching Protocol With D2D-Aided UAV-NOMA Communications in Large-Scale Networks

Graph-Based File Dispatching Protocol With D2D-Aided UAV-NOM...

引用

IEEE Conference on Wireless Communications and Networking

作者： Baoji Wang Rongqing Zhang Chen Chen Xiang Cheng Liuqing Yan State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronics School of Electronics Engineering and Computer Science Peking University Beijing China school of Software Engineering Tongji University Shanghai China Department of Electrical & Computer Engineering Colorado State University CO USA

ISBN: (数字)9781728131061

ISBN: (纸本)9781728131078

Unmanned aerial vehicle (UAV)-assisted communications are expected to become an important part of the next generation mobile communication systems, due to the high mobility of the UAVs. Non-orthogonal multiple access (NOMA) is regarded as a rosy technology in the fifth generation (5G) mobile communication systems, since it can effectively improve the spectral efficiency. In this paper, we combine the advantages of the UAV-assisted communications and NOMA, and propose a device-to-device (D2D)-enhanced UAV-NOMA network architecture, in which D2D is introduced to increase the file dispatching efficiency. Resource reuse based on spatial reuse is also allowed to further improve the spectral efficiency. Then, we propose a graph-based file dispatching (GFD) protocol to control the interference and minimize the UAV-assisted file dispatching mission time. Simulation results verify the advantages of our proposed D2D-enhanced UAV-NOMA network architecture and the efficiency of our designed GFD protocol.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Protected Bidding Against Compromised Information Injection in IoT-Based Smart Grid 2nd

Protected Bidding Against Compromised Information Injection ...

引用

2nd EAI International Conference on Smart Grid and Internet of Things, SGIoT 2018

作者： Bhuiyan, Md Zakirul Alam Zaman, Mdaliuz Wang, Guojun Wang, Tian Rahman, Md. Arafat Tao, Hai Department of Computer and Information Science Fordham University New York CityNY United States School of Computer Science and Educational Software Guangzhou University Guangzhou China Department of Computer Science and Technology Huaqiao University Xiamen China Faculty of Computer Systems and Software Engineering Universiti Malaysia Pahang Pekan Malaysia Department of Computer Science Baoji University of Arts and Sciences BaojiShaanxi China

ISBN: (纸本)9783030059279

The smart grid is regarded as one of the important application field of the Internet of Things (IoT) composed of embedded sensors, which sense and control the behavior of the energy world. IoT is attractive for features of grid catastrophe prevention and decrease of grid transmission line and reliable load fluctuation control. Automated Demand Response (ADR) in smart grids maintain demand-supply stability and in regulating customer side electric energy charges. An important goal of IoT-based demand-response using IoT is to enable a type of DR approach called automatic demand bidding (ADR-DB). However, compromised information board can be injected into during the DR process that influences the data privacy and security in the ADR-DB bidding process, while protecting privacy oriented consumer data is in the bidding process is must. In this work, we present a bidding approach that is secure and private for incentive-based ADR system. We use cryptography method instead of using any trusted third-party for the security and privacy. We show that proposed ADR bidding are computationally practical through simulations performed in three simulation environments. © 2019, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Efficient Quantum State Tracking in Noisy Environments

arXiv

引用

arXiv 2022年

作者： Rambach, Markus Youssry, Akram Tomamichel, Marco Romero, Jacquiline Australian Research Council Centre of Excellence for Engineered Quantum Systems School of Mathematics and Physics University of Queensland QLD4072 Australia University of Technology Sydney Centre for Quantum Software and Information UltimoNSW2007 Australia Quantum Photonics Laboratory Centre for Quantum Computation and Communication Technology RMIT University MelbourneVIC3000 Australia Department of Electrical and Computer Engineering Centre for Quantum Technologies National University of Singapore Singapore119077 Singapore

Quantum state tomography, which aims to find the best description of a quantum state-the density matrix, is an essential building block in quantum computation and communication. Standard techniques for state tomography are incapable of tracking changing states and often perform poorly in the presence of environmental noise. Although there are different approaches to solve these problems theoretically, experimental demonstrations have so far been sparse. Our approach, matrix-exponentiated gradient tomography, is an online tomography method that allows for state tracking, updates the estimated density matrix dynamically from the very first measurements, is computationally efficient, and converges to a good estimate quickly even with noisy data. The algorithm is controlled via a single parameter, its learning rate, which determines the performance and can be tailored in simulations to the individual experiment. We present an experimental implementation of matrix-exponentiated gradient tomography on a qutrit system encoded in the transverse spatial mode of photons. We investigate the performance of our method on stationary and evolving states, as well as significant environmental noise, and find fidelities of around 95% in all cases. © 2022, CC BY.

关键词： Tomography

来源：评论

学校读者我要写书评

暂无评论

Synergy of edge intelligence and blockchain: a comprehensive survey

TechRxiv

引用

TechRxiv 2021年

作者： Wang, Xiaofei Ren, Xiaoxu Qiu, Chao Xiong, Zehui Yao, Haipeng Leung, Victor C.M. College of Intelligence and Computing Tianjin University Tianjin300350 China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100088 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518061 China Department of Electrical and Computer Engineering The University of British Columbia VancouverBCV6T 1Z4 Canada

Edge intelligence (EI), as an emerging technology, has been attracting significant attention. It pushes the frontier of artificial intelligence (AI) from the cloud to the network edge, aiming to embrace and support the next-generation communications while unleashing AI services. However, it faces challenges in its decentralized management and security, which limit its capabilities to support services with numerous requirements. On the other side, blockchain (BC), as a promising decentralized technology, is beneficial to tackle the above issues. However, there exist some technical challenges for BC, such as transaction capacity, scalability, and fault tolerance. Motivated by significant current interest around EI and BC, this survey examines whether the synergy of EI and BC can make a powerful network with combined functionalities of both cutting-edge technologies. Accordingly, we develop EI-chain and Chain-intelligence to realize reliable computing-power management, data administration, and model optimization at the edges, while improving the functions of BC by leveraging complementary characteristics of EI and BC, further making up for their own limitations. In this survey, a wide spectrum of literature is carefully reviewed to enable the EI-chain and Chain-intelligence. Moreover, we cover the technological aspects of EI-chain and Chain-intelligence: overview, motivations, and frameworks. Finally, some challenges and future directions are explored. We believe this survey will provide developers and researchers a comprehensive view on the synergy of EI and BC, while accelerating the design of a powerful integrated network. © 2021, CC BY-NC-SA.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

FedMint: Intelligent Bilateral Client Selection in Federated Learning with Newcomer IoT Devices

arXiv

引用

arXiv 2022年

作者： Wehbi, Osama Arisdakessian, Sarhad Wahab, Omar Abdel Otrok, Hadi Otoum, Safa Mourad, Azzam Guizani, Mohsen Cyber Security Systems and Applied AI Research Center Department of CSM Lebanese American University Lebanon Department of Computer and Software Engineering Polytechnique Montréal MontrealQC Canada Khalifa University Abu Dhabi United Arab Emirates College of Technological Innovation Zayed University Dubai United Arab Emirates Division of Science New York University Abu Dhabi United Arab Emirates Mohammad Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

Federated Learning (FL) is a novel distributed privacy-preserving learning paradigm, which enables the collaboration among several participants (e.g., Internet of Things devices) for the training of machine learning models. However, selecting the participants that would contribute to this collaborative training is highly challenging. Adopting a random selection strategy would entail substantial problems due to the heterogeneity in terms of data quality, and computational and communication resources across the participants. Although several approaches have been proposed in the literature to overcome the problem of random selection, most of these approaches follow a unilateral selection strategy. In fact, they base their selection strategy on only the federated server’s side, while overlooking the interests of the client devices in the process. To overcome this problem, we present in this paper FedMint, an intelligent client selection approach for federated learning on IoT devices using game theory and bootstrapping mechanism. Our solution involves the design of: (1) preference functions for the client IoT devices and federated servers to allow them to rank each other according to several factors such as accuracy and price, (2) intelligent matching algorithms that take into account the preferences of both parties in their design, and (3) bootstrapping technique that capitalizes on the collaboration of multiple federated servers in order to assign initial accuracy value for the newly connected IoT devices. Based on our simulation findings, our strategy surpasses the VanillaFL selection approach in terms of maximizing both the revenues of the client devices and accuracy of the global federated learning model. © 2022, CC BY-NC-SA.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：